Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4123 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7275. Min Act: -0.0000

Data Index: 351882 (C4 (Web Text))

Max Activating Token Index: 947

Text #1

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7280. Min Act: -0.0000

Data Index: 1063656 (C4 (Web Text))

Max Activating Token Index: 792

Text #2

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.7066. Min Act: -0.0000

Data Index: 531266 (C4 (Web Text))

Max Activating Token Index: 453

Text #3

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6120. Min Act: -0.0000

Data Index: 588315 (C4 (Web Text))

Max Activating Token Index: 702

Text #4

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6533. Min Act: -0.0000

Data Index: 572598 (C4 (Web Text))

Max Activating Token Index: 466

Text #5

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6586. Min Act: -0.0000

Data Index: 1402109 (Python Code)

Max Activating Token Index: 64

Text #6

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6468. Min Act: -0.0000

Data Index: 558529 (C4 (Web Text))

Max Activating Token Index: 624

Text #7

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.6464. Min Act: -0.0000

Data Index: 1056378 (C4 (Web Text))

Max Activating Token Index: 146

Text #8

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5685. Min Act: -0.0000

Data Index: 631732 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5864. Min Act: -0.0000

Data Index: 1137163 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5840. Min Act: -0.0000

Data Index: 1415141 (Python Code)

Max Activating Token Index: 146

Text #11

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5989. Min Act: -0.0000

Data Index: 185212 (C4 (Web Text))

Max Activating Token Index: 81

Text #12

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5580. Min Act: -0.0000

Data Index: 1128820 (C4 (Web Text))

Max Activating Token Index: 150

Text #13

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5526. Min Act: -0.0000

Data Index: 860980 (C4 (Web Text))

Max Activating Token Index: 461

Text #14

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5678. Min Act: -0.0000

Data Index: 1113180 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5465. Min Act: -0.0000

Data Index: 390091 (C4 (Web Text))

Max Activating Token Index: 219

Text #16

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5485. Min Act: -0.0000

Data Index: 868178 (C4 (Web Text))

Max Activating Token Index: 626

Text #17

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5471. Min Act: -0.0000

Data Index: 655980 (C4 (Web Text))

Max Activating Token Index: 388

Text #18

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5114. Min Act: -0.0000

Data Index: 1544368 (Python Code)

Max Activating Token Index: 395

Text #19

Max Range: 0.7280. Min Range: -0.7280

Max Act: 0.5437. Min Act: -0.0000

Data Index: 585518 (C4 (Web Text))

Max Activating Token Index: 94